@inproceedings{camacho-gonzalez-etal-2026-l52,
title = "L52+-{IIMAS}-{UNAM} at {S}em{E}val-2026 Task 1 ({MWAHAHA}): Joke Selection Through a Multi-Stage Prompt-Engineering and Heuristic Pipeline",
author = "Camacho Gonzalez, Adolfo Tonatihu and
Cruz, Ximena and
God{\'i}nez-Aldana, Natalia and
Palacios-Pati{\~n}o, Lizeth and
Rangel, Ram{\'o}n and
Meza Ruiz, Ivan Vladimir",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.291/",
pages = "2301--2306",
ISBN = "979-8-89176-414-9",
abstract = "Humor generation remains one of the most challenging tasks in natural language processing, requiring creativity, incongruity resolution, cultural sensitivity, and strict structural control. We present a fully prompt-based system for headline-conditioned joke generation in SemEval-2026 Task 1 (MWAHAHA) for both English and Spanish. Deliberately avoiding fine-tuning, our approach relies on structured prompt engineering combined with a multi-stage heuristic pipeline. For Spanish, we extract a ``stylistic-humor DNA'' from a public joke corpus to guide generation. The pipeline integrates multi-candidate generation, diversity enhancement, iterative refinement, LLM-based rewriting, and constraint-aware selection. Human evaluation performed by the team (n=180) shows substantial gains over single-pass generation, particularly in funniness and punchline clarity. Official shared-task results were modest (12th/16 Spanish, 24th/31 English), underscoring that limited originality remains a key bottleneck. In an era dominated by large language models (LLMs) such as GPT-4o and Grok, our work demonstrates the value of linguistically grounded heuristics as an efficient, interpretable, and low-cost complement to black-box generation systems."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="camacho-gonzalez-etal-2026-l52">
<titleInfo>
<title>L52+-IIMAS-UNAM at SemEval-2026 Task 1 (MWAHAHA): Joke Selection Through a Multi-Stage Prompt-Engineering and Heuristic Pipeline</title>
</titleInfo>
<name type="personal">
<namePart type="given">Adolfo</namePart>
<namePart type="given">Tonatihu</namePart>
<namePart type="family">Camacho Gonzalez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ximena</namePart>
<namePart type="family">Cruz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalia</namePart>
<namePart type="family">Godínez-Aldana</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lizeth</namePart>
<namePart type="family">Palacios-Patiño</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramón</namePart>
<namePart type="family">Rangel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>Humor generation remains one of the most challenging tasks in natural language processing, requiring creativity, incongruity resolution, cultural sensitivity, and strict structural control. We present a fully prompt-based system for headline-conditioned joke generation in SemEval-2026 Task 1 (MWAHAHA) for both English and Spanish. Deliberately avoiding fine-tuning, our approach relies on structured prompt engineering combined with a multi-stage heuristic pipeline. For Spanish, we extract a “stylistic-humor DNA” from a public joke corpus to guide generation. The pipeline integrates multi-candidate generation, diversity enhancement, iterative refinement, LLM-based rewriting, and constraint-aware selection. Human evaluation performed by the team (n=180) shows substantial gains over single-pass generation, particularly in funniness and punchline clarity. Official shared-task results were modest (12th/16 Spanish, 24th/31 English), underscoring that limited originality remains a key bottleneck. In an era dominated by large language models (LLMs) such as GPT-4o and Grok, our work demonstrates the value of linguistically grounded heuristics as an efficient, interpretable, and low-cost complement to black-box generation systems.</abstract>
<identifier type="citekey">camacho-gonzalez-etal-2026-l52</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.291/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2301</start>
<end>2306</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T L52+-IIMAS-UNAM at SemEval-2026 Task 1 (MWAHAHA): Joke Selection Through a Multi-Stage Prompt-Engineering and Heuristic Pipeline
%A Camacho Gonzalez, Adolfo Tonatihu
%A Cruz, Ximena
%A Godínez-Aldana, Natalia
%A Palacios-Patiño, Lizeth
%A Rangel, Ramón
%A Meza Ruiz, Ivan Vladimir
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F camacho-gonzalez-etal-2026-l52
%X Humor generation remains one of the most challenging tasks in natural language processing, requiring creativity, incongruity resolution, cultural sensitivity, and strict structural control. We present a fully prompt-based system for headline-conditioned joke generation in SemEval-2026 Task 1 (MWAHAHA) for both English and Spanish. Deliberately avoiding fine-tuning, our approach relies on structured prompt engineering combined with a multi-stage heuristic pipeline. For Spanish, we extract a “stylistic-humor DNA” from a public joke corpus to guide generation. The pipeline integrates multi-candidate generation, diversity enhancement, iterative refinement, LLM-based rewriting, and constraint-aware selection. Human evaluation performed by the team (n=180) shows substantial gains over single-pass generation, particularly in funniness and punchline clarity. Official shared-task results were modest (12th/16 Spanish, 24th/31 English), underscoring that limited originality remains a key bottleneck. In an era dominated by large language models (LLMs) such as GPT-4o and Grok, our work demonstrates the value of linguistically grounded heuristics as an efficient, interpretable, and low-cost complement to black-box generation systems.
%U https://aclanthology.org/2026.semeval-1.291/
%P 2301-2306
Markdown (Informal)
[L52+-IIMAS-UNAM at SemEval-2026 Task 1 (MWAHAHA): Joke Selection Through a Multi-Stage Prompt-Engineering and Heuristic Pipeline](https://aclanthology.org/2026.semeval-1.291/) (Camacho Gonzalez et al., SemEval 2026)
ACL